# Parlel

> Search people, companies and open roles on Parlel, an open professional network.

- name: com.parlel/parlel
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 97/100
- quality: 83/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.parlel%2Fparlel
- tools: https://api.protogrid.dev/v1/servers/com.parlel%2Fparlel/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "parlel": {
      "type": "http",
      "url": "https://api.parlel.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 85
- provenance: 100
- drivers: +repository +namespace-matches-repo +dns-namespace +website +reachable +uptime-100% ~updated-41d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 83/100 (good)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: get_job (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_person (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); search_jobs (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 1,139 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 8, about 1,139 tokens to load them all
- tool set hash: 54022d7f85a6888ba6ce7e5c1acab518
- badge: [![protogrid quality](https://protogrid.dev/badge/com.parlel/parlel.svg)](https://protogrid.dev/servers/com.parlel/parlel)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://api.parlel.com/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (8)

- `get_agent`: One published agent by slug: its brief, schedule and recent findings with sources.
- `get_company`: One company by handle, with its open roles inline.
- `get_job`: One role by id, with its full description, skills, pay and the hiring company. Works for closed roles too; read `status`.
- `get_person`: One published profile by handle: headline, bio, work history, education, skills, recent posts and the agents they publish.
- `search_agents`: Published watch agents -- standing searches people run against the open web -- with a preview of what each has found. No text filter; walk the list. `sort` is `recent` or `popular`.
- `search_companies`: Companies with a published page. `q` matches name, tagline or industry; `industry` is an exact label; `hiring=true` narrows to companies with at least one open role. Each item has `open_role_count`.
- `search_jobs`: Open roles on Parlel, newest first. `q` matches the TITLE only. Filter by working arrangement, seniority and a pay floor. Returns {items, next_cursor}; each item has a `role_url` you can cite.
- `search_people`: Published profiles. `q` matches name, headline, company, role and work history (not skills, not bio). `skills` are exact tags, AND-ed. `based_in` is where the person is; `location` also matches where they would move to. Contact details are never returned.